0
$\begingroup$

I know that if a P value is less than 0.05 we can reject the null hypothesis and state that the finding may be statistically significant however I remember reading something about if the 95% confidence interval includes 0 that its not a significant finding or something like that (i tried to find what i was reading but couldnt find it again).

Im just wonder, if we have a p value below 0.05 but have a confidence interval including 0, how do we interpret this? Do we say that it is statistically significant but likely being caused by other factors?

$\endgroup$
0
$\begingroup$

Im just wonder, if we have a p value below 0.05 but have a confidence interval including 0, how do we interpret this?

It means that you took a confidence interval with more than 95% confidence. This is technically possible, but misleading to take the confidence interval at another $\alpha$ level than your test.

Existing software packages will give you p-values and CIs for the same $\alpha$ unless you force them to do something else.

$\endgroup$
  • $\begingroup$ Thanks for the help, I've been sitting here for ages trying to work this out and just realized it was 0.1 not 0.01 for my p value ugh. $\endgroup$ – Mick Dec 23 '17 at 12:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.